{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QCMRM4BT276LGKCIGNMHCLOWW4","short_pith_number":"pith:QCMRM4BT","schema_version":"1.0","canonical_sha256":"8099167033d7fcb328483358712dd6b703e720fa39cbb178b2900c847f5a8a7a","source":{"kind":"arxiv","id":"2103.06268","version":2},"attestation_state":"computed","paper":{"title":"CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anya Chen, Collin Burns, Dan Hendrycks, Spencer Ball","submitted_at":"2021-03-10T18:59:34Z","abstract_excerpt":"Many specialized domains remain untouched by deep learning, as large labeled datasets require expensive expert annotators. We address this bottleneck within the legal domain by introducing the Contract Understanding Atticus Dataset (CUAD), a new dataset for legal contract review. CUAD was created with dozens of legal experts from The Atticus Project and consists of over 13,000 annotations. The task is to highlight salient portions of a contract that are important for a human to review. We find that Transformer models have nascent performance, but that this performance is strongly influenced by"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2103.06268","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-10T18:59:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ac0c072984f2789c400bf8d9f49b1c5ea4f6f7796bac23f9917d63fdef49c2ba","abstract_canon_sha256":"e5efd4d41e29b25d0114f2cf6d55363ba936792966d392c80bc5963840a4db0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:09.892672Z","signature_b64":"kjEuhbPxsoJH0Gwl7eHorB+bouplO+2BlMw7V5nEBnvWkNbwL4z0wKONi4Wlke5m4E1pkWD8COsMblmqXfucBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8099167033d7fcb328483358712dd6b703e720fa39cbb178b2900c847f5a8a7a","last_reissued_at":"2026-07-05T03:30:09.892176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:09.892176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anya Chen, Collin Burns, Dan Hendrycks, Spencer Ball","submitted_at":"2021-03-10T18:59:34Z","abstract_excerpt":"Many specialized domains remain untouched by deep learning, as large labeled datasets require expensive expert annotators. We address this bottleneck within the legal domain by introducing the Contract Understanding Atticus Dataset (CUAD), a new dataset for legal contract review. CUAD was created with dozens of legal experts from The Atticus Project and consists of over 13,000 annotations. The task is to highlight salient portions of a contract that are important for a human to review. We find that Transformer models have nascent performance, but that this performance is strongly influenced by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06268","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.06268/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2103.06268","created_at":"2026-07-05T03:30:09.892232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.06268v2","created_at":"2026-07-05T03:30:09.892232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06268","created_at":"2026-07-05T03:30:09.892232+00:00"},{"alias_kind":"pith_short_12","alias_value":"QCMRM4BT276L","created_at":"2026-07-05T03:30:09.892232+00:00"},{"alias_kind":"pith_short_16","alias_value":"QCMRM4BT276LGKCI","created_at":"2026-07-05T03:30:09.892232+00:00"},{"alias_kind":"pith_short_8","alias_value":"QCMRM4BT","created_at":"2026-07-05T03:30:09.892232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05901","citing_title":"Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29170","citing_title":"UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29738","citing_title":"Multi-Legal-Bench: Evaluating LLMs on Legal Reasoning Across Jurisdictions, Languages, and Legal Traditions","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16767","citing_title":"Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10186","citing_title":"LegalCiteBench: Evaluating Citation Reliability in Legal Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05532","citing_title":"A Few Good Clauses: Comparing LLMs vs Domain-Trained Small Language Models on Structured Contract Extraction","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10853","citing_title":"A Benchmark for Gap and Overlap Analysis as a Test of KG Task Readiness","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QCMRM4BT276LGKCIGNMHCLOWW4","json":"https://pith.science/pith/QCMRM4BT276LGKCIGNMHCLOWW4.json","graph_json":"https://pith.science/api/pith-number/QCMRM4BT276LGKCIGNMHCLOWW4/graph.json","events_json":"https://pith.science/api/pith-number/QCMRM4BT276LGKCIGNMHCLOWW4/events.json","paper":"https://pith.science/paper/QCMRM4BT"},"agent_actions":{"view_html":"https://pith.science/pith/QCMRM4BT276LGKCIGNMHCLOWW4","download_json":"https://pith.science/pith/QCMRM4BT276LGKCIGNMHCLOWW4.json","view_paper":"https://pith.science/paper/QCMRM4BT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.06268&json=true","fetch_graph":"https://pith.science/api/pith-number/QCMRM4BT276LGKCIGNMHCLOWW4/graph.json","fetch_events":"https://pith.science/api/pith-number/QCMRM4BT276LGKCIGNMHCLOWW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QCMRM4BT276LGKCIGNMHCLOWW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QCMRM4BT276LGKCIGNMHCLOWW4/action/storage_attestation","attest_author":"https://pith.science/pith/QCMRM4BT276LGKCIGNMHCLOWW4/action/author_attestation","sign_citation":"https://pith.science/pith/QCMRM4BT276LGKCIGNMHCLOWW4/action/citation_signature","submit_replication":"https://pith.science/pith/QCMRM4BT276LGKCIGNMHCLOWW4/action/replication_record"}},"created_at":"2026-07-05T03:30:09.892232+00:00","updated_at":"2026-07-05T03:30:09.892232+00:00"}